© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 129500
    Prev
    Next
    INDEX
    Explanations

    references to processes and actions related to the implementation and evaluation of community projects and programs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocker
    -0.07
     something
    -0.07
    èİ
    -0.07
     someone
    -0.06
     ÑħÑĢа
    -0.06
    ?t
    -0.06
    ÇIJ
    -0.06
    iks
    -0.06
    igs
    -0.06
    something
    -0.06
    POSITIVE LOGITS
     this
    0.10
    this
    0.10
    =this
    0.09
    	this
    0.08
     these
    0.08
    (this
    0.08
     ÑįÑĤой
    0.07
    [this
    0.07
     questa
    0.07
    ãĢģãģĵãģ®
    0.07
    Activations Density 0.050%

    No Known Activations